Back to leaderboard

huihui-qwen3.6-35b-a3b-claude-4.7-opus-abliterated-mtp

LM-STUDIO GGUF

qwen35moe · 35B · Q4_K

Excellent

Jun 12, 2026 · AMD Ryzen 5 5600X 6-Core Processor

qwen3-coder:30b

OLLAMA GGUF

qwen3moe · 30.5B · Q4_K_M

Excellent

Jun 18, 2026 · AMD Ryzen 5 5500U

Global Score
88 vs 82
Hardware Fit
94 vs 71
Quality Score
85 vs 87

Hardware

huihui-qwen3.6-35b… qwen3-coder:30b
MachineGigabyte Technology Co., Ltd. B550M AORUS PROHP HP Pavilion Laptop 15-eh1xxx
CPUAMD Ryzen 5 5600X 6-Core ProcessorAMD Ryzen 5 5500U
Cores1212
RAM47 GB63 GB
GPUAD106 [GeForce RTX 4060 Ti]AMD Radeon(TM) Graphics
OScachyos rollingMicrosoft Windows 10 Enterprise LTSC 10.0.19044
Archx64x64
Power Modelow-powerbalanced

Performance

huihui-qwen3.6-35b… qwen3-coder:30b
Tokens/sec39.814.3
First chunk3 ms869 ms
TTFT479 ms869 ms
Load timeN/A0.3 s
Memory usage24.4 GB20.5 GB
Memory %52%32%

HW Fit Score Breakdown

huihui-qwen3.6-35b-a3b-…

Speed
50/50
TTFT
20/20
Memory
24/30

qwen3-coder:30b

Speed
22/50
TTFT
20/20
Memory
29/30

Quality

huihui-qwen3.6-35b-a3b-…

Reasoning
18/20
Coding
17/20
Instruction
13/20
Structured
14/15
Math
13/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Adequate Structured Output: Strong Math: Strong Multilingual: Strong

qwen3-coder:30b

Reasoning
16/20
Coding
19/20
Instruction
16/20
Structured
15/15
Math
11/15
Multilingual
10/10
Reasoning: Strong Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Strong Multilingual: Strong

Run yours and compare

$ npm install -g metrillm@latest
$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest